Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 6257
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and their respective institutions

    oai_token-act-pair · gpt-3.5-turbo

    references to official reports and government statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cherokee
    -1.00
     Appalachian
    -0.99
     Native
    -0.93
     BLM
    -0.92
    Utah
    -0.90
    Native
    -0.89
     weeds
    -0.88
    Alabama
    -0.88
     Tribe
    -0.86
     Clemson
    -0.85
    POSITIVE LOGITS
     Gö
    1.35
    ü
    1.31
     Mü
    1.31
     EUR
    1.24
    å
    1.22
    euro
    1.19
     âĤ¬
    1.18
    ische
    1.17
    liga
    1.16
    ür
    1.15
    Activations Density 0.576%

    No Known Activations